FRACTAL FEATURES FOR DIAGNOSING MAMMOGRAPHIC MASSES

用于诊断乳房 X 线摄影肿块的分形特征

• 批准号: 2651907
• 负责人: ALAN I. PENN
• 金额: $ 10万
• 依托单位: ALAN PENN AND ASSOCIATES, INC.
• 依托单位国家: 美国
• 财政年份: 1998
• 资助国家: 美国
• 起止时间: 1998-04-01 至 1999-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/2651907
• 关键词: artificial intelligence; breast neoplasm /cancer diagnosis; computer assisted diagnosis; computer program /software; computer system design /evaluation; diagnosis design /evaluation; mathematical model; neoplasm /cancer classification /staging; statistics /biometry

We propose developing statistical fractal features which quantify lesion border roughness on mammograms and using these features to distinguish malignant and benign breast lesions. Objective measures of lesion roughness are important in the diagnosis and staging of breast cancer. In this novel approach, we generate a space of fractal models, and evaluate the fractal dimension (fd) of the lesion from the statistics of the model space. Using intensity as the third dimension, we generate a 3-dimensional image of the mammogram and select a set of intensity levels found in the lesion. For each selected intensity level, we construct a binary thresholded image and trace the lesion border. Analysis is restricted to segments of thresholded borders which are in high-gradient portions of the 3-dimensional image and can be determined with high precision. Each selected boundary segments is analyzed to identify self-affine subsegments which are modeled using multiple fractal interpolation functions having known fd values. Thus we construct a large sample space of fd values which are computed from high-precision boundary traces occurring on a range of threshold levels. The statistics of the fd sample space are the features used to distinguish between malignant and benign lesions. PROPOSED COMMERCIAL APPLICATION Our product will have significant value to the diagnostician who must distinguish malignant from benign breast lesions. The algorithm is readily integrated into both computer-aided diagnosis systems and digital mammogram systems which display and process mammographic images for the expert diagnostician.

我们建议开发量化病变的统计分形特征 乳房X光照片上的边界粗糙度并使用这些特征来区分 恶性和良性乳腺病变。 病变的客观测量 粗糙度对于乳腺癌的诊断和分期很重要。 在这种新颖的方法中，我们生成了一个分形模型空间，并且 从统计数据中评估病变的分形维数 (fd) 的模型空间。 使用强度作为第三个维度，我们生成一个三维 乳房 X 光照片的图像，并选择一组在 病变。 对于每个选定的强度级别，我们构建一个二进制 阈值图像并追踪病变边界。 分析受到限制 到高梯度部分的阈值边界段 3维图像的图像，并且可以高精度地确定。 分析每个选定的边界段以识别自仿射 使用多重分形插值建模的子段 具有已知 fd 值的函数。 因此我们构建了一个大样本 从高精度边界计算出的 fd 值的空间 出现在一系列阈值水平上的痕迹。 的统计数据 fd样本空间是用来区分恶性的特征 和良性病变。 拟议的商业应用 我们的产品对于诊断医生来说具有重要价值，他们必须 区分恶性和良性乳腺病变。 算法是 易于集成到计算机辅助诊断系统和 显示和处理乳房 X 光图像的数字乳房 X 光检查系统 对于专家诊断医生来说。